---
type: Agentic Web Standard
title: "Agent Skills"
description: "How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?"
resource: "https://agentskills.io/specification"
tags: ["act", "document-format", "linux-foundation", "describe-agent-capabilities", "expose-tools-to-agents"]
status: stable
generated: { by: agenticweb-builder/1.0, at: 2026-10-30T00:00:00Z }
verified: { by: process:agenticweb-engine, at: 2026-10-28T00:00:00Z }
stale_after: 2026-11-27T00:00:00Z
sources:
  - id: ref-1
    resource: "https://agentskills.io/specification"
    title: "Agent Skills, Specification - Agent Skills, checked 2026-10-28 (text checked at the page's Markdown copy, specification.md): \"A skill is a directory containing, at minimum, a SKILL.md file\" \"The SKILL.md file must contain YAML frontmatter followed by Markdown content.\" \"Max 64 characters. Lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen.\" \"Must not contain consecutive hyphens (--)\" \"Must match the parent directory name\" \"Max 1024 characters. Non-empty. Describes what the skill does and when to use it.\" \"License name or reference to a bundled license file.\" \"Max 500 characters. Indicates environment requirements (intended product, system packages, network access, etc.).\" \"Arbitrary key-value mapping for additional metadata (a map from string keys to string values).\" \"Space-separated string of pre-approved tools the skill may use. (Experimental)\" \"100 tokens): The name and description fields are loaded at startup for all skills\" \"5000 tokens recommended): The full SKILL.md body is loaded when the skill is activated\" \"Keep your main SKILL.md under 500 lines.\" \"This checks that your SKILL.md frontmatter is valid and follows all naming conventions.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-2
    resource: "https://agentskills.io/home"
    title: "Agent Skills, Agent Skills Overview - Agent Skills, checked 2026-10-28: \"Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows.\" \"The Agent Skills format was originally developed by Anthropic, released as an open standard, and has been adopted by a growing number of agent products.\" \"Agents load skills through progressive disclosure, in three stages:\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-3
    resource: "https://github.com/agentskills/agentskills"
    title: "agentskills, agentskills/agentskills GitHub repository (\"Specification and documentation for Agent Skills\"; created 2025-12-16; licence Apache-2.0; no GitHub releases), checked 2026-10-28 (metadata checked through the GitHub API): \"Specification and documentation for Agent Skills\" \"\"created_at\": \"2025-12-16\" \"\"spdx_id\": \"Apache-2.0\"\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-4
    resource: "https://claude.com/resources/articles/skills"
    title: "Anthropic, Introducing Agent Skills | Claude by Anthropic, 2025-10-16, with an update dated 2025-12-18: \"Now, you can build your own skills and use them across Claude apps, Claude Code, and our API.\" \"Update: We've added organization-wide management for skills, a directory featuring partner-built skills, and published Agent Skills as an open standard for cross-platform portability. (December 18, 2025)\""
    last_modified: 2025-10-16T00:00:00Z
  - id: ref-5
    resource: "https://www.anthropic.com/research/equipping-agents-for-the-real-world-with-agent-skills"
    title: "Anthropic, Equipping agents for the real world with Agent Skills (Anthropic engineering), 2025-10-16: \"This led us to create Agent Skills: organized folders of instructions, scripts, and resources that agents can discover and load dynamically to perform better at specific tasks.\" \"This metadata is the first level of progressive disclosure\" \"We'll also explore how Skills can complement Model Context Protocol (MCP) servers by teaching agents more complex workflows that involve external tools and software.\""
    last_modified: 2025-10-16T00:00:00Z
  - id: ref-6
    resource: "https://claude.com/resources/articles/organization-skills-and-directory"
    title: "Anthropic, Skills for organizations, partners, the ecosystem | Claude by Anthropic, 2025-12-18: \"We're also publishing Agent Skills as an open standard.\" \"Like MCP, we believe skills should be portable across tools and platforms\""
    last_modified: 2025-12-18T00:00:00Z
  - id: ref-7
    resource: "https://www.anthropic.com/news/donating-agent-skills-to-the-agentic-ai-foundation"
    title: "Anthropic, Donating Agent Skills to the Agentic AI Foundation, 2026-10-22: \"We developed skills while working on Claude Code.\" \"Today, we're donating Agent Skills, the open standard that gives AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF).\" \"We are donating the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain.\" \"Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers.\" \"You can continue to use the standard or contribute to it without joining the AAIF.\" \"We've proposed starting with a roadmap covering versioned releases, a formal proposal process, and security guidance for people who write and install skills.\""
    last_modified: 2026-10-22T00:00:00Z
  - id: ref-8
    resource: "https://www.linuxfoundation.org/press/agentic-ai-foundation-announces-four-new-projects-agent-skills-open-responses-openenv-and-opensandbox"
    title: "Linux Foundation, Agentic AI Foundation Announces Four New Projects: Agent Skills, Open Responses, OpenEnv, and OpenSandbox (press release), 2026-10-22: \"AAIF announced four new projects: Agent Skills, contributed by Anthropic;\" \"They join the Agent2Agent (A2A) protocol, Agent Router, agentgateway, AGENTS.md, goose, and the Model Context Protocol (MCP) as AAIF projects, all operating under AAIF's open, vendor-neutral governance.\""
    last_modified: 2026-10-22T00:00:00Z
  - id: ref-9
    resource: "https://aaif.io/blog/agent-skills-sharing-team-expertise-across-ai-agents"
    title: "Angie Jones, Agent Skills: Open Standard for Sharing AI Agent Workflows - Agentic AI Foundation (AAIF) (AAIF blog), 2026-10-22: \"Bringing the project to AAIF will ensure neutral governance from a multi-company Technical Steering Committee that will guide its future.\" \"The specification is open source under Apache 2.0 and CC BY 4.0\""
    last_modified: 2026-10-22T00:00:00Z
  - id: ref-10
    resource: "https://github.com/cloudflare/agent-skills-discovery-rfc"
    title: "Cloudflare, cloudflare/agent-skills-discovery-rfc README (Agent Skills Discovery via Well-Known URIs, draft v0.2.0, published 2026-01-17, updated 2026-03-12), checked 2026-10-28 (text checked at the raw.githubusercontent.com copy): \"Status: Draft\" \"Version: 0.2.0\" \"Published Date: 2026-01-17\" \"Updated Date: 2026-03-12\" \"Publishers MUST provide an index at:\" \"rename well-known URI from /.well-known/skills/ to /.well-known/agent-skills/\" \"Register agent-skills as a well-known URI suffix.\" \"replace files array and package object with a flat single-artifact model: each skill entry now has type (\"skill-md\" or \"archive\"), url, and digest\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-11
    resource: "https://www.iana.org/assignments/well-known-uris/well-known-uris-1.csv"
    title: "IANA, Well-Known URIs registry (CSV export), checked 2026-10-28"
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-12
    resource: "https://modelcontextprotocol.io/community/working-groups/skills-over-mcp"
    title: "Model Context Protocol, Skills Over MCP Charter - Model Context Protocol, checked 2026-10-28: \"The Skills Over MCP Working Group defines how\" \"The WG maintains the official Skills extension (io.modelcontextprotocol/skills) in modelcontextprotocol/ext-skills.\" \"SEP-2640 is Final, merged on September 13, 2026.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-13
    resource: "https://agenticresourcediscovery.org/spec/"
    title: "ards-project, ARD Specification - AgenticResourceDiscovery.org (v0.91), checked 2026-10-28 (text checked at the raw spec/ard.md copy): \"application/agent-skills+md — Agent Skill defined in Markdown\" \"application/agent-skills+zip / application/agent-skills+gzip — packaged Agent Skill archive\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-14
    resource: "https://agents.md/"
    title: "AGENTS.md, AGENTS.md, checked 2026-10-28: \"Think of AGENTS.md as a README for agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-15
    resource: "https://code.claude.com/docs/en/skills"
    title: "Anthropic, Extend Claude with skills - Claude Code Docs, checked 2026-10-28: \"Claude Code skills follow the Agent Skills open standard, which works across multiple AI tools.\" \"Claude Code extends the standard with additional features like invocation control, subagent execution, and dynamic context injection.\" \"Unlike CLAUDE.md content, a skill's body loads only when it's used, so long reference material costs almost nothing until you need it.\" \"~/.claude/skills/<skill-name>/SKILL.md\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-16
    resource: "https://learn.chatgpt.com/docs/build-skills"
    title: "OpenAI, Build skills | ChatGPT Learn (undated), checked 2026-10-28: \"Skills build on the open agent skills standard.\" \"ChatGPT and Codex start with each skill's name and description, then load the full SKILL.md instructions when they decide to use that skill.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-17
    resource: "https://github.blog/changelog/2025-12-18-github-copilot-now-supports-agent-skills/"
    title: "GitHub, GitHub Copilot now supports Agent Skills - GitHub Changelog, 2025-12-18: \"You can now create Agent Skills to teach Copilot how to perform specialized tasks in a specific, repeatable way.\" \"They work across Copilot coding agent, Copilot CLI, and agent mode in Visual Studio Code Insiders.\""
    last_modified: 2025-12-18T00:00:00Z
  - id: ref-18
    resource: "https://code.visualstudio.com/docs/agent-customization/agent-skills"
    title: "Microsoft, Use Agent Skills in VS Code (VS Code documentation, undated), checked 2026-10-28: \"Agent Skills is an open standard that works across multiple AI agents, including GitHub Copilot in VS Code, GitHub Copilot CLI, the GitHub Copilot app, and the experimental OpenAI Codex integration.\" \"~/.copilot/skills/, ~/.claude/skills/, ~/.agents/skills/\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-19
    resource: "https://geminicli.com/docs/changelogs/"
    title: "Google, Gemini CLI release notes | Gemini CLI (v0.23.0, 2026-01-07): \"Experimental Agent Skills Support in Preview: Gemini CLI now supports Agent Skills in our preview builds.\""
    last_modified: 2026-01-07T00:00:00Z
  - id: ref-20
    resource: "https://geminicli.com/docs/cli/skills/"
    title: "Google, Agent Skills | Gemini CLI (documentation), checked 2026-10-28: \"Based on the Agent Skills open standard, a \"skill\" is a self-contained directory that packages instructions and assets into a discoverable capability.\" \"Unlike general context files (GEMINI.md), which provide persistent workspace-wide background, Skills represent on-demand expertise.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-21
    resource: "https://cursor.com/changelog/2-4"
    title: "Cursor, Subagents, Skills, and Image Generation · Cursor (changelog 2.4), 2026-01-22: \"Cursor now supports Agent Skills in the editor and CLI.\""
    last_modified: 2026-01-22T00:00:00Z
  - id: ref-22
    resource: "https://cursor.com/docs/skills"
    title: "Cursor, Agent Skills | Cursor Docs, checked 2026-10-28: \"Agent Skills is an open standard. Learn more at agentskills.io.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-23
    resource: "https://ampcode.com/news/agent-skills"
    title: "Amp, Agent Skills - Amp, 2025-12-10: \"Amp supports agent skills.\""
    last_modified: 2025-12-10T00:00:00Z
  - id: ref-24
    resource: "https://goose-docs.ai/docs/guides/context-engineering/using-skills/"
    title: "goose, Agent Skills | goose | Your open source AI agent (documentation, undated), checked 2026-10-28: \"Place a SKILL.md file inside a named subdirectory.\" \"For example, a global skill called code-review goes in ~/.agents/skills/code-review/SKILL.md.\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-25
    resource: "https://github.com/anthropics/skills"
    title: "Anthropic, anthropics/skills GitHub repository (\"Public repository for Agent Skills\"), checked 2026-10-28: \"Public repository for Agent Skills\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-26
    resource: "https://github.com/huggingface/skills"
    title: "Hugging Face, huggingface/skills GitHub repository (\"Give your agents the power of the Hugging Face ecosystem\"), checked 2026-10-28: \"Give your agents the power of the Hugging Face ecosystem\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-27
    resource: "https://developers.cloudflare.com/.well-known/agent-skills/index.json"
    title: "Cloudflare, developers.cloudflare.com/.well-known/agent-skills/index.json, checked 2026-10-28: \"https://schemas.agentskills.io/discovery/0.2.0/schema.json\" \"agents-sdk\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-28
    resource: "https://vercel.com/.well-known/agent-skills/index.json"
    title: "Vercel, vercel.com/.well-known/agent-skills/index.json, checked 2026-10-28: \"https://schemas.agentskills.io/discovery/0.2.0/schema.json\" \"deploy-to-vercel\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-29
    resource: "https://docs.stripe.com/.well-known/skills/index.json"
    title: "Stripe, docs.stripe.com/.well-known/skills/index.json, checked 2026-10-28: \"connect-recommend\" \"SKILL.md\""
    last_modified: 2026-10-28T00:00:00Z
  - id: ref-30
    resource: "https://thenewstack.io/agent-skills-anthropics-next-bid-to-define-ai-standards/"
    title: "Frederic Lardinois, The New Stack, Agent Skills: Anthropic's Next Bid to Define AI Standards - The New Stack, 2025-12-18: \"Today, Anthropic is launching the Agent Skills spec as an open standard in a move that feels similar to how it turned its Model Context Protocol (MCP) into the de facto standard for how AI agents use tools today.\""
    last_modified: 2025-12-18T00:00:00Z
  - id: ref-31
    resource: "https://the-decoder.com/anthropic-publishes-agent-skills-as-an-open-standard-for-ai-platforms/"
    title: "Matthias Bastian, The Decoder, Anthropic publishes Agent Skills as an open standard for AI platforms, 2025-12-18: \"Anthropic is releasing \"Agent Skills\" as an open standard at agentskills.io.\""
    last_modified: 2025-12-18T00:00:00Z
  - id: ref-32
    resource: "https://www.techrepublic.com/article/news-anthropic-agent-skills-foundation-handover/"
    title: "Aminu Abdullahi, TechRepublic, Anthropic Hands Over Agent Skills: What IT Teams Should Know, 2026-10-26: \"Anthropic is handing its AI agent playbook to an industry foundation, betting that shared standards will help software agents work across competing platforms.\""
    last_modified: 2026-10-26T00:00:00Z
---

# Agent Skills

Agent Skills is an agentic-web standard (document format — /.well-known/agent-skills/index.json) at step 5, Act, governed by Agentic AI Foundation, under the Linux Foundation, since 2026-10-22, when Anthropic contributed the standard as an AAIF project; its status is "Published as an open standard on 2025-12-18". It answers: "How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?" Replacing or extending Package README / plugin manifest, implementation status is multi-implementation, last verified 2026-10-28.

# Overview

Agent Skills is an open format for giving AI agents specialised knowledge and workflows: a skill is a folder holding a SKILL.md file of instructions, with optional scripts, references and other resources [^ref-2][^ref-1]. The agent reads only each skill's name and description at startup, then loads the full instructions and any bundled files when a task calls for them; this is called progressive disclosure [^ref-2][^ref-5]. Anthropic launched skills for Claude in October 2025, published the format as an open standard at agentskills.io in December 2025, and donated it to the Agentic AI Foundation in October 2026 [^ref-4][^ref-6][^ref-7]. Coding agents from Anthropic, OpenAI, GitHub and Microsoft, Google, Cursor and others now say they support the format [^ref-15][^ref-16][^ref-17][^ref-18][^ref-20][^ref-22].

# Examples

```http
GET /.well-known/agent-skills/index.json
# parse: JSON object with $schema (https://schemas.agentskills.io/discovery/0.2.0/schema.json) and a skills[] array of entries with name, type, description, url, and digest (sha256:...); local packages validate via YAML frontmatter in {skill-name}/SKILL.md
# on absent: 404 or non-JSON at /.well-known/agent-skills/index.json means the origin does not publish a web skill discovery index; local Agent Skills packages may still be distributed via repositories or local skill directories.
```

# Knowledge Graph

* **Lifecycle Step**: [5 Act](/category/act/index.md)
* **Pairs with**: [Model Context Protocol](/okf/protocols/mcp.md), [AGENTS.md](/okf/protocols/agents-md.md), [llms.txt](/okf/protocols/llms-txt.md), [Open Agentic Schema Framework](/okf/protocols/oasf.md), [Open Knowledge Format](/okf/protocols/okf.md), [Agent Context Interchange Protocol](/okf/protocols/acip.md)
* **Related terms**: [Agent skill](/okf/terms/agent-skill.md), [SKILL.md](/okf/terms/skill-md.md)
* **Compared in**: [OpenAPI & REST APIs vs Model Context Protocol (MCP) (classic vs agentic)](/compare/openapi-vs-mcp/index.md), [DOM Browser Automation vs WebMCP & MCP (classic vs agentic)](/compare/browser-automation-vs-webmcp/index.md), [Agent Skills vs Model Context Protocol](/compare/anthropic-agent-skills-format-vs-mcp/index.md), [WebMCP vs Agent Skills](/compare/webmcp-vs-anthropic-agent-skills-format/index.md), [Agent Skills vs AGENTS.md](/compare/anthropic-agent-skills-format-vs-agents-md/index.md), [Agent Skills vs llms.txt](/compare/anthropic-agent-skills-format-vs-llms-txt/index.md)

[^ref-1]: Agent Skills, Specification - Agent Skills, checked 2026-10-28 (text checked at the page's Markdown copy, specification.md): "A skill is a directory containing, at minimum, a SKILL.md file" "The SKILL.md file must contain YAML frontmatter followed by Markdown content." "Max 64 characters. Lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen." "Must not contain consecutive hyphens (--)" "Must match the parent directory name" "Max 1024 characters. Non-empty. Describes what the skill does and when to use it." "License name or reference to a bundled license file." "Max 500 characters. Indicates environment requirements (intended product, system packages, network access, etc.)." "Arbitrary key-value mapping for additional metadata (a map from string keys to string values)." "Space-separated string of pre-approved tools the skill may use. (Experimental)" "100 tokens): The name and description fields are loaded at startup for all skills" "5000 tokens recommended): The full SKILL.md body is loaded when the skill is activated" "Keep your main SKILL.md under 500 lines." "This checks that your SKILL.md frontmatter is valid and follows all naming conventions." (https://agentskills.io/specification)
[^ref-2]: Agent Skills, Agent Skills Overview - Agent Skills, checked 2026-10-28: "Agent Skills are a lightweight, open format for extending AI agent capabilities with specialized knowledge and workflows." "The Agent Skills format was originally developed by Anthropic, released as an open standard, and has been adopted by a growing number of agent products." "Agents load skills through progressive disclosure, in three stages:" (https://agentskills.io/home)
[^ref-3]: agentskills, agentskills/agentskills GitHub repository ("Specification and documentation for Agent Skills"; created 2025-12-16; licence Apache-2.0; no GitHub releases), checked 2026-10-28 (metadata checked through the GitHub API): "Specification and documentation for Agent Skills" ""created_at": "2025-12-16" ""spdx_id": "Apache-2.0"" (https://github.com/agentskills/agentskills)
[^ref-4]: Anthropic, Introducing Agent Skills | Claude by Anthropic, 2025-10-16, with an update dated 2025-12-18: "Now, you can build your own skills and use them across Claude apps, Claude Code, and our API." "Update: We've added organization-wide management for skills, a directory featuring partner-built skills, and published Agent Skills as an open standard for cross-platform portability. (December 18, 2025)" (https://claude.com/resources/articles/skills)
[^ref-5]: Anthropic, Equipping agents for the real world with Agent Skills (Anthropic engineering), 2025-10-16: "This led us to create Agent Skills: organized folders of instructions, scripts, and resources that agents can discover and load dynamically to perform better at specific tasks." "This metadata is the first level of progressive disclosure" "We'll also explore how Skills can complement Model Context Protocol (MCP) servers by teaching agents more complex workflows that involve external tools and software." (https://www.anthropic.com/research/equipping-agents-for-the-real-world-with-agent-skills)
[^ref-6]: Anthropic, Skills for organizations, partners, the ecosystem | Claude by Anthropic, 2025-12-18: "We're also publishing Agent Skills as an open standard." "Like MCP, we believe skills should be portable across tools and platforms" (https://claude.com/resources/articles/organization-skills-and-directory)
[^ref-7]: Anthropic, Donating Agent Skills to the Agentic AI Foundation, 2026-10-22: "We developed skills while working on Claude Code." "Today, we're donating Agent Skills, the open standard that gives AI agents specialized knowledge and workflows, to the Agentic AI Foundation (AAIF)." "We are donating the Agent Skills name and logo, the GitHub organization, and the agentskills.io domain." "Engineers from Anthropic, Google, OpenAI, and other companies will maintain the standard as individuals, with David Soria Parra and Mahesh Murag as Lead Maintainers." "You can continue to use the standard or contribute to it without joining the AAIF." "We've proposed starting with a roadmap covering versioned releases, a formal proposal process, and security guidance for people who write and install skills." (https://www.anthropic.com/news/donating-agent-skills-to-the-agentic-ai-foundation)
[^ref-8]: Linux Foundation, Agentic AI Foundation Announces Four New Projects: Agent Skills, Open Responses, OpenEnv, and OpenSandbox (press release), 2026-10-22: "AAIF announced four new projects: Agent Skills, contributed by Anthropic;" "They join the Agent2Agent (A2A) protocol, Agent Router, agentgateway, AGENTS.md, goose, and the Model Context Protocol (MCP) as AAIF projects, all operating under AAIF's open, vendor-neutral governance." (https://www.linuxfoundation.org/press/agentic-ai-foundation-announces-four-new-projects-agent-skills-open-responses-openenv-and-opensandbox)
[^ref-9]: Angie Jones, Agent Skills: Open Standard for Sharing AI Agent Workflows - Agentic AI Foundation (AAIF) (AAIF blog), 2026-10-22: "Bringing the project to AAIF will ensure neutral governance from a multi-company Technical Steering Committee that will guide its future." "The specification is open source under Apache 2.0 and CC BY 4.0" (https://aaif.io/blog/agent-skills-sharing-team-expertise-across-ai-agents)
[^ref-10]: Cloudflare, cloudflare/agent-skills-discovery-rfc README (Agent Skills Discovery via Well-Known URIs, draft v0.2.0, published 2026-01-17, updated 2026-03-12), checked 2026-10-28 (text checked at the raw.githubusercontent.com copy): "Status: Draft" "Version: 0.2.0" "Published Date: 2026-01-17" "Updated Date: 2026-03-12" "Publishers MUST provide an index at:" "rename well-known URI from /.well-known/skills/ to /.well-known/agent-skills/" "Register agent-skills as a well-known URI suffix." "replace files array and package object with a flat single-artifact model: each skill entry now has type ("skill-md" or "archive"), url, and digest" (https://github.com/cloudflare/agent-skills-discovery-rfc)
[^ref-11]: IANA, Well-Known URIs registry (CSV export), checked 2026-10-28 (https://www.iana.org/assignments/well-known-uris/well-known-uris-1.csv)
[^ref-12]: Model Context Protocol, Skills Over MCP Charter - Model Context Protocol, checked 2026-10-28: "The Skills Over MCP Working Group defines how" "The WG maintains the official Skills extension (io.modelcontextprotocol/skills) in modelcontextprotocol/ext-skills." "SEP-2640 is Final, merged on September 13, 2026." (https://modelcontextprotocol.io/community/working-groups/skills-over-mcp)
[^ref-13]: ards-project, ARD Specification - AgenticResourceDiscovery.org (v0.91), checked 2026-10-28 (text checked at the raw spec/ard.md copy): "application/agent-skills+md — Agent Skill defined in Markdown" "application/agent-skills+zip / application/agent-skills+gzip — packaged Agent Skill archive" (https://agenticresourcediscovery.org/spec/)
[^ref-14]: AGENTS.md, AGENTS.md, checked 2026-10-28: "Think of AGENTS.md as a README for agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project." (https://agents.md/)
[^ref-15]: Anthropic, Extend Claude with skills - Claude Code Docs, checked 2026-10-28: "Claude Code skills follow the Agent Skills open standard, which works across multiple AI tools." "Claude Code extends the standard with additional features like invocation control, subagent execution, and dynamic context injection." "Unlike CLAUDE.md content, a skill's body loads only when it's used, so long reference material costs almost nothing until you need it." "~/.claude/skills/<skill-name>/SKILL.md" (https://code.claude.com/docs/en/skills)
[^ref-16]: OpenAI, Build skills | ChatGPT Learn (undated), checked 2026-10-28: "Skills build on the open agent skills standard." "ChatGPT and Codex start with each skill's name and description, then load the full SKILL.md instructions when they decide to use that skill." (https://learn.chatgpt.com/docs/build-skills)
[^ref-17]: GitHub, GitHub Copilot now supports Agent Skills - GitHub Changelog, 2025-12-18: "You can now create Agent Skills to teach Copilot how to perform specialized tasks in a specific, repeatable way." "They work across Copilot coding agent, Copilot CLI, and agent mode in Visual Studio Code Insiders." (https://github.blog/changelog/2025-12-18-github-copilot-now-supports-agent-skills/)
[^ref-18]: Microsoft, Use Agent Skills in VS Code (VS Code documentation, undated), checked 2026-10-28: "Agent Skills is an open standard that works across multiple AI agents, including GitHub Copilot in VS Code, GitHub Copilot CLI, the GitHub Copilot app, and the experimental OpenAI Codex integration." "~/.copilot/skills/, ~/.claude/skills/, ~/.agents/skills/" (https://code.visualstudio.com/docs/agent-customization/agent-skills)
[^ref-19]: Google, Gemini CLI release notes | Gemini CLI (v0.23.0, 2026-01-07): "Experimental Agent Skills Support in Preview: Gemini CLI now supports Agent Skills in our preview builds." (https://geminicli.com/docs/changelogs/)
[^ref-20]: Google, Agent Skills | Gemini CLI (documentation), checked 2026-10-28: "Based on the Agent Skills open standard, a "skill" is a self-contained directory that packages instructions and assets into a discoverable capability." "Unlike general context files (GEMINI.md), which provide persistent workspace-wide background, Skills represent on-demand expertise." (https://geminicli.com/docs/cli/skills/)
[^ref-21]: Cursor, Subagents, Skills, and Image Generation · Cursor (changelog 2.4), 2026-01-22: "Cursor now supports Agent Skills in the editor and CLI." (https://cursor.com/changelog/2-4)
[^ref-22]: Cursor, Agent Skills | Cursor Docs, checked 2026-10-28: "Agent Skills is an open standard. Learn more at agentskills.io." (https://cursor.com/docs/skills)
[^ref-23]: Amp, Agent Skills - Amp, 2025-12-10: "Amp supports agent skills." (https://ampcode.com/news/agent-skills)
[^ref-24]: goose, Agent Skills | goose | Your open source AI agent (documentation, undated), checked 2026-10-28: "Place a SKILL.md file inside a named subdirectory." "For example, a global skill called code-review goes in ~/.agents/skills/code-review/SKILL.md." (https://goose-docs.ai/docs/guides/context-engineering/using-skills/)
[^ref-25]: Anthropic, anthropics/skills GitHub repository ("Public repository for Agent Skills"), checked 2026-10-28: "Public repository for Agent Skills" (https://github.com/anthropics/skills)
[^ref-26]: Hugging Face, huggingface/skills GitHub repository ("Give your agents the power of the Hugging Face ecosystem"), checked 2026-10-28: "Give your agents the power of the Hugging Face ecosystem" (https://github.com/huggingface/skills)
[^ref-27]: Cloudflare, developers.cloudflare.com/.well-known/agent-skills/index.json, checked 2026-10-28: "https://schemas.agentskills.io/discovery/0.2.0/schema.json" "agents-sdk" (https://developers.cloudflare.com/.well-known/agent-skills/index.json)
[^ref-28]: Vercel, vercel.com/.well-known/agent-skills/index.json, checked 2026-10-28: "https://schemas.agentskills.io/discovery/0.2.0/schema.json" "deploy-to-vercel" (https://vercel.com/.well-known/agent-skills/index.json)
[^ref-29]: Stripe, docs.stripe.com/.well-known/skills/index.json, checked 2026-10-28: "connect-recommend" "SKILL.md" (https://docs.stripe.com/.well-known/skills/index.json)
[^ref-30]: Frederic Lardinois, The New Stack, Agent Skills: Anthropic's Next Bid to Define AI Standards - The New Stack, 2025-12-18: "Today, Anthropic is launching the Agent Skills spec as an open standard in a move that feels similar to how it turned its Model Context Protocol (MCP) into the de facto standard for how AI agents use tools today." (https://thenewstack.io/agent-skills-anthropics-next-bid-to-define-ai-standards/)
[^ref-31]: Matthias Bastian, The Decoder, Anthropic publishes Agent Skills as an open standard for AI platforms, 2025-12-18: "Anthropic is releasing "Agent Skills" as an open standard at agentskills.io." (https://the-decoder.com/anthropic-publishes-agent-skills-as-an-open-standard-for-ai-platforms/)
[^ref-32]: Aminu Abdullahi, TechRepublic, Anthropic Hands Over Agent Skills: What IT Teams Should Know, 2026-10-26: "Anthropic is handing its AI agent playbook to an industry foundation, betting that shared standards will help software agents work across competing platforms." (https://www.techrepublic.com/article/news-anthropic-agent-skills-foundation-handover/)